© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8346
    Prev
    Next
    INDEX
    Explanations

    references to loved ones, particularly in the context of loss or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.22
    4:0.02
    5:0.05
    6:0.11
    7:0.16
    8:0.04
    9:0.04
    10:0.11
    11:0.10
    Negative Logits
    Effective
    -1.25
    OH
    -1.09
    soDeliveryDate
    -1.08
    urat
    -1.07
    IOR
    -1.07
    perture
    -1.04
    tm
    -1.04
    Channel
    -1.04
    Poly
    -1.00
    OUGH
    -0.99
    POSITIVE LOGITS
     dearly
    1.17
     companions
    1.15
     sacrific
    1.09
     spouse
    1.07
     sisters
    1.07
     spo
    1.02
     reunion
    1.01
     prostitutes
    0.99
     martyr
    0.97
     spont
    0.97
    Activations Density 0.007%

    No Known Activations